Discriminative Deep Metric Learning for Face Verification in the Wild

By Junlin Hu, Jiwen Lu, Yap-Peng Tan. 2014

738 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences (2015, methodology): “Then, we show how to train a Siamese CNN to learn a feature transformation from the image space into the latent style space.”
Few-Shot Adversarial Domain Adaptation (2017, methodology): “We address that problem by modifying the usual pairing technique used in many applications such as learning similarity metrics [7, 23, 22].”
SphereFace: Deep Hypersphere Embedding for Face Recognition (2017, background): “Recently, prevailing deep metric learning [7, 17, 24, 30, 25, 22, 34] usually uses neural networks to automatically learn discriminative features x1,x2 followed by a simple distance metric such as Euclidean distance ‖x1−x2‖2.”
Actions ~ Transformations (2015, methodology): “To model the transformation, we apply a Siamese network architecture in this paper, which is also related to the literature using deep metric learning [11, 9, 37, 12, 54, 16].”
Learning Two-Branch Neural Networks for Image-Text Matching Tasks (2017, background): “Such within-view neighborhood preservation constraints have been extensively explored in the metric learning literature [38], [39], [40], [41], [42], [43].”
Deep Learning Face Representation by Joint Identification-Verification (2014, background): “In recent years, a great deal of efforts have been made for face recognition with deep learning [5, 10, 20, 27, 8, 22, 21].”
End-to-End Learning of Deep Visual Representations for Image Retrieval (2016, background): “2015), and performing face identification (Chopra et al. 2005; Hu et al. 2014; Sun et al. 2014).”
Deeply learned face representations are sparse, selective, and robust (2014, neutral): “6 DDML (combined) [12] 82 .”
Graph Matching Networks for Learning the Similarity of Graph Structured Objects (2019, background): “…recently the ideas of distance metric learning and representation learning have been combined in applications like face veriﬁcation, where deep convolutional neural networks are learned to map similar images to similar representation vectors (Chopra et al., 2005; Hu et al., 2014; Sun et al., 2014).”
A Discriminative Feature Learning Approach for Deep Face Recognition (2016, background): “[13] learn a nonlinear transformations and yield discriminative deep metric with a margin between positive and negative face image pairs.”
Online Deep Metric Learning (2018, background): “Existing DML algorithms can be broadly classified into two categories: (1) Convolutional neural networks (CNNs) combined with metric loss [5, 23, 27]; (2) Multilayer perceptron (MLP) (or Fully connected layers) combined with metric loss [10, 11].”
Integrating parametric and non-parametric models for scene labeling (2015, methodology): “We replace the softmax layer of previous CNN (CNN-softmax) with a fully connected layer parameterized by W (or more layers to learn non-linear metrics [10]) and fix the biases to be zero, which serves as a Mahalanobis metric (M = WW ).”
High-fidelity Pose and Expression Normalization for face recognition in the wild (2015, methodology): “The discriminative deep metric learning (DDML) [26] and the joint Bayesian (JB) [20] are used for restricted and unrestricted settings, respectively.”
L2-constrained Softmax Loss for Discriminative Face Verification (2017, background): “Hu et al. [13] designed a discriminative deep metric with a margin between positive and negative face pairs.”
When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs (2018, methodology): “To reduce the number of free parameters in the proposed D-CNN model, we introduce an intermediate parameter τ to connect τ1 and τ2 by following the work in [64].”
Labeled Faces in the Wild: A Survey (2016, background): “23 Discriminative deep metric learning for face verification in the wild, 2014 [41]”
Revisiting Training Strategies and Generalization Performance in Deep Metric Learning (2020, background): “…become increasingly important for applications ranging from image retrieval (Movshovitz-Attias et al., 2017; Roth et al., 2019; Wu et al., 2017; Lin et al., 2018) to zero-shot classification (Schroff et al., 2015; Sanakoyeu et al., 2019) and face verification (Hu et al., 2014; Liu et al., 2017).”